Adaptive conversation support bot

Abstract

Systems and techniques for adaptive conversation support bot are described herein. An audio stream may be obtained including a conversation of a first user. An event may be identified in the conversation using the audio stream. A first keyword phrase may be extracted from the audio stream in response to identification of the event. The audio stream may be searched for a second keyword phrase based on the first keyword phrase. An action may be performed based on the first keyword phrase and the second keyword phrase. Results of the action may be out via a context appropriate output channel. The context appropriate output channel may be determined based on a context of the conversation and a privacy setting of the first user.

What is claimed is: 
     
       1. A system for facilitating conversational analysis, the system comprising:
 at least one processor; and 
 memory including instructions that, when executed by the at least one processor, cause the at least one processor to perform operations to:
 obtain an audio stream including a conversation of a first user; 
 identify an event in the conversation using the audio stream; 
 in response to identification of the event, extract a first keyword phrase from the audio stream; 
 search the audio stream for a second keyword phrase using the first keyword phrase; 
 perform an action based on the first keyword phrase and the second keyword phrase; 
 create a rule for the performed action based on the first keyword phrase and the second keyword phrase with a machine learning engine; 
 receive feedback on the action performed based on the rule; 
 modify the machine learning engine over time with the feedback to create a modified rule for performing actions; 
 determine an environment associated with the conversation; and 
 output results of the action via a context appropriate output channel, the context appropriate output channel determined based on a context of the conversation and the environment associated with the conversation. 
 
 
     
     
       2. The system of  claim 1 , where the instructions further cause the processor to perform operations to:
 identify a characteristic associated with the context appropriate output channel wherein the results of the action are output on the context appropriate output channel using a first medium; and 
 output the results of the action on the context appropriate output channel using a second medium different from the first medium based on the identified characteristic associated with the context appropriate output channel. 
 
     
     
       3. The system of  claim 2 , wherein the first medium is audio and the second medium is text. 
     
     
       4. The system of  claim 1 , wherein the conversation is between the first user and a second user and the event is a word in the conversation and the second keyword phrase is searched for using the word in the first keyword phrase. 
     
     
       5. The system of  claim 4 , where the instructions further cause the processor to perform operations to identify the second user and the instructions to perform the action include instructions to use the second keyword phrase to search a first data source and a second data source, wherein the first data source corresponds to the first user and the second data source corresponds to the second user. 
     
     
       6. The system of  claim 4 , where the instructions further cause the processor to perform operations to:
 determine a relationship between the first user and the second user; 
 identify a privacy setting based on the relationship between the first user and the second user; and 
 identify the context appropriate output channel based on the privacy setting. 
 
     
     
       7. The system of  claim 1 , where the instructions further cause the processor to perform operations to:
 determine a location of the conversation; and 
 select the context appropriate output channel based on the determined location of the conversation. 
 
     
     
       8. At least one non-transitory machine readable medium including instruction for facilitating conversational analysis that, when executed by a machine, cause the machine to perform operations to:
 obtain an audio stream including a conversation of a first user; 
 identify an event in the conversation using the audio stream; 
 in response to identification of the event, extract a first keyword phrase from the audio stream; 
 search the audio stream for a second keyword phrase using the first keyword phrase; 
 perform an action based on the first keyword phrase and the second keyword phrase; 
 create a rule for the performed action based on the first keyword phrase and the second keyword phrase with a machine learning engine; 
 receive feedback on the action performed based on the rule; 
 modify the machine learning engine over time with the feedback to create a modified rule for performing actions; 
 determine an environment associated with the conversation; and 
 output results of the action via a context appropriate output channel, the context appropriate output channel determined based on a context of the conversation and the environment associated with the conversation. 
 
     
     
       9. The non-transitory machine readable medium of  claim 8 , further comprising instructions to:
 identify a characteristic associated with the context appropriate output channel wherein the results of the action are output on the context appropriate output channel using a first medium; and 
 output the results of the action on the context appropriate output channel using a second medium different from the first medium based on the identified characteristic associated with the context appropriate output channel. 
 
     
     
       10. The non-transitory machine readable medium of  claim 9 , wherein the first medium is audio and the second medium is text. 
     
     
       11. The non-transitory machine readable medium of  claim 8 , wherein the conversation is between the first user and a second user and the event is a word in the conversation and the second keyword phrase is searched for using the word in the first keyword phrase. 
     
     
       12. The non-transitory machine readable medium of  claim 11 , further comprising instructions to identify the second user and the instructions to perform the action include instructions to use the second keyword phrase to search a first data source and a second data source, wherein the first data source corresponds to the first user and the second data source corresponds to the second user. 
     
     
       13. The non-transitory machine readable medium of  claim 11 , further comprising instructions to:
 determine a relationship between the first user and the second user; 
 identify a privacy setting based on the relationship between the first user and the second user; and 
 identify the context appropriate output channel based on the privacy setting. 
 
     
     
       14. The non-transitory machine readable medium of  claim 8 , further comprising instructions to:
 determine a location of the conversation; and 
 select the context appropriate output channel based on the determined location of the conversation. 
 
     
     
       15. A method for facilitating conversational analysis, the method comprising:
 obtaining an audio stream including a conversation of a first user; 
 identifying an event in the conversation using the audio stream; 
 in response to identification of the event, extracting a first keyword phrase from the audio stream; 
 searching the audio stream for a second keyword phrase using the first keyword phrase; 
 performing an action based on the first keyword phrase and the second keyword phrase; 
 creating a rule for the performed action based on the first keyword phrase and the second keyword phrase with a machine learning engine; 
 receiving feedback on the action performed based on the rule; 
 modifying the machine learning engine over time with the feedback to create a modified rule for performing actions; 
 determining an environment associated with the conversation; and 
 outputting results of the action via a context appropriate output channel, the context appropriate output channel determined based on a context of the conversation and the environment associated with the conversation. 
 
     
     
       16. The method of  claim 15 , further comprising instructions to:
 identify a characteristic associated with the context appropriate output channel wherein the results of the action are output on the context appropriate output channel using a first medium; and 
 output the results of the action on the context appropriate output channel using a second medium different from the first medium based on the identified characteristic associated with the context appropriate output channel, wherein the first medium is audio and the second medium is text. 
 
     
     
       17. The method of  claim 15 , wherein the conversation is between the first user and a second user and the event is a word in the conversation and the second keyword phrase is searched for using the word in the first keyword phrase. 
     
     
       18. The method of  claim 17 , further comprising instructions to identify the second user and the instructions to perform the action include instructions to use the second keyword phrase to search a first data source and a second data source, wherein the first data source corresponds to the first user and the second data source corresponds to the second user. 
     
     
       19. The method of  claim 17 , further comprising instructions to:
 determine a relationship between the first user and the second user; 
 identify a privacy setting based on the relationship between the first user and the second user; and 
 identify the context appropriate output channel based on the privacy setting. 
 
     
     
       20. The method of  claim 15 , further comprising instructions to:
 determine a location of the conversation; and 
 select the context appropriate output channel based on the determined location of the conversation.